© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198204
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    at
    0.71
    i
    0.68
    en
    0.65
    u
    0.59
    as
    0.58
    ient
    0.56
     a
    0.55
    ig
    0.53
     should
    0.50
    ก
    0.50
    POSITIVE LOGITS
     мелдеш
    0.55
     потреб
    0.54
     острова
    0.54
     नव्ह
    0.53
     укреп
    0.53
     вверх
    0.52
     праз
    0.51
     расходов
    0.51
     два
    0.50
     подве
    0.50
    Activations Density 0.000%

    No Known Activations